WO2019012437A1 - A device for sound based monitoring of machine operations and method for operating the same - Google Patents

A device for sound based monitoring of machine operations and method for operating the same Download PDF

Info

Publication number
WO2019012437A1
WO2019012437A1 PCT/IB2018/055097 IB2018055097W WO2019012437A1 WO 2019012437 A1 WO2019012437 A1 WO 2019012437A1 IB 2018055097 W IB2018055097 W IB 2018055097W WO 2019012437 A1 WO2019012437 A1 WO 2019012437A1
Authority
WO
WIPO (PCT)
Prior art keywords
sound
machine
processor
predefined
models
Prior art date
Application number
PCT/IB2018/055097
Other languages
French (fr)
Inventor
Anand Deshpande
Aniruddha PANT
Original Assignee
Anand Deshpande
Pant Aniruddha
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anand Deshpande, Pant Aniruddha filed Critical Anand Deshpande
Priority to JP2020523832A priority Critical patent/JP2020527816A/en
Priority to US16/627,176 priority patent/US10976730B2/en
Publication of WO2019012437A1 publication Critical patent/WO2019012437A1/en

Links

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/18Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/406Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
    • G05B19/4065Monitoring tool breakage, life or condition
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00Testing or monitoring of control systems or parts thereof
    • G05B23/02Electric testing or monitoring
    • G05B23/0205Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0243Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
    • G05B23/0254Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00Testing or monitoring of control systems or parts thereof
    • G05B23/02Electric testing or monitoring
    • G05B23/0205Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0259Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
    • G05B23/0267Fault communication, e.g. human machine interface [HMI]
    • G05B23/027Alarm generation, e.g. communication protocol; Forms of alarm
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18Status alarms
    • G08B21/187Machine fault alarms
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00Program-control systems
    • G05B2219/30Nc systems
    • G05B2219/37Measurements
    • G05B2219/37214Detect failed machine component, machine performance degradation
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00Program-control systems
    • G05B2219/30Nc systems
    • G05B2219/37Measurements
    • G05B2219/37337Noise, acoustic emission, sound

Definitions

  • Embodiments of a present disclosure relate to sound analytics and more particularly to, a device for sound based monitoring of machine operations and method for operating the same.
  • faults should be detected in the initial stage as possible or before a failure of the machine may cause a shutdown.
  • the failure or beginning of failure of any machine may be accompanied by characteristic sounds. The cause of the undesirable sound needs to be identified for the machine to continue machine's serviceable life.
  • Various fault detection techniques more particularly to fault detection techniques with acoustic monitoring are available to detect the fault in the early stage or before failure.
  • acoustic sensor which may use sound inputs.
  • acoustic sensors are incapable of analysing complex sounds.
  • sensors are designed for identifying very specific sound signature and their functionality is unchangeable over time.
  • the available acoustic sensors only use a threshold checking and give an alarm or indication whenever the threshold is crosses.
  • such sensors do not provide the in-depth analysis of sound and sometimes leads to ambiguous results.
  • the available acoustic sensors can only be used to monitor a specific problem with the machines. Such sensors may not be used to monitor overall operations of the machines, and extract statistics about the machine operations as well as machine performance including quality of the operations.
  • a device for monitoring sound of a machine includes a sound detection device located in proximity to the machine and configured to collect a plurality of sound signals in real-time from the machine.
  • the device also includes a processor electrically coupled to the sound detection device.
  • the processor is configured to acquire one or more predefined sound analytics models associated with the machine.
  • the processor is also configured to analyse the plurality of sound signals based on the one or more predefined sound analytics models.
  • the processor is further configured to identify an operating condition of the machine based on analysed result and the one or more predefined sound analytics models.
  • the device further includes a sound analytics engine operatively coupled to the processor.
  • the sound analytics system is configured to update the one or more predefined models based on the plurality of sound signals.
  • a method for operating a sound monitoring device includes collecting, by a sound detection device, a plurality of sound signals in real-time from the machine.
  • the method also includes acquiring, by a processor, one or more predefined sound analytics models associated with the machine.
  • the method further includes analysing, by the processor, the plurality of sound signals based on the one or more predefined sound analytics model.
  • the method further includes identifying, by the processor, an operating condition of the machine based on analysed result and the one or more predefined sound analytics models.
  • the method further includes updating, by a sound analytics system, the one or more sound analytics models based on the plurality of sound signals.
  • FIG. 1 illustrates a block diagram of a device for sound based monitoring machine operations in accordance with an embodiment of the present disclosure
  • FIG. 2 illustrates a block diagram of an exemplary sound monitoring device of FIG. 1 in accordance with an embodiment of the present disclosure
  • FIG. 3 illustrates a flow chart representing the steps involved in a method for operating the sound monitoring device of FIG. 1 in accordance with an embodiment of the present disclosure.
  • elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale.
  • one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
  • Embodiments of the present disclosure relate to a device for sound based monitoring of machine operations.
  • the device includes a sound detection device located in proximity to the machine and configured to collect a plurality of sound signals in real-time from the machine.
  • the device also includes a processor electrically coupled to the sound detection device.
  • the processor is configured to acquire one or more predefined sound analytics models associated with the machine.
  • the processor is also configured to analyse the plurality of sound signals based on the one or more predefined sound analytics models.
  • the processor is further configured to identify an operating condition of the machine based on analysed result and the one or more predefined sound analytics models.
  • the device further includes a sound analytics engine operatively coupled to the processor.
  • the sound analytics system is further configured to update the one or more sound analytics models based on the plurality of sound signals.
  • FIG. 1 is a block diagram of a sound monitoring device (10) in accordance with an embodiment of the present disclosure.
  • the device (10) for monitoring sound of a machine is configured to perform edge computing by receiving a plurality of sound signals from the machine.
  • edge computing refers to a capability of the device (10) to perform local computing within the device and without requiring a connectivity to the servers.
  • 'sound' includes both audible and inaudible sounds. In other words, 'sounds' includes sounds that are audible to humans, and sounds that are below the human audible range (subsonic) and sounds that are above the human audible range (ultrasonic).
  • the device (10) include a casing configured to enclose sound detection device (40), a processor (20), a sound analytics system (50), a memory device (30) and a plurality of peripheral devices.
  • the device (10) may include a processor (20), a memory device (30) and a plurality of peripheral devices.
  • the device (10) also includes a sound detection device (40) located in proximity to the machine.
  • the sound detection device (40) is configured to collect a plurality of sound signals in real-time from the machine.
  • the sound detection device (40) may include a microphone.
  • the sound detection device (40) may be located outside the casing.
  • at least one of one or more sound detection devices (40) may be located inside the casing.
  • the sound detection device (40) is also configured to convert the plurality of sounds in the plurality of electrical signals.
  • the device (10) also includes the processor (20) electrically coupled to the sound detection device (40).
  • the processor (20) is configured to receive the plurality of electrical signals from the sound detection device (40) and store the plurality electrical signals in the memory device (30).
  • the processor (20) is also configured to acquire one or more predefined sound analytics models associated with the machine.
  • the processor (20) is also configured to analyse the plurality of electrical signals based on the one or more predefined sound analytics models.
  • the one or more predefined sound analytics models may include a plurality of machine learning models.
  • the one or more predefined sound analytics models may be stored in the memory device (30).
  • the processor (20) is further configured to identify the operating condition of the machine based on an analysed result and the one or more predefined sound analytics models.
  • the processor (20) is further configured to identify one or more faults of the machine based on an analysed result and the one or more predefined sound analytics models.
  • the device (10) further includes a sound analytics system (50) operatively coupled to the processor (20).
  • the sound analytics system (50) is configured to update the one or more predefined sound analytics models based on the plurality of sound signals.
  • the sound analytics system (50) may receive the plurality of sound signals and learns from the plurality of sound signals continuously for detecting one or more faults in the future.
  • the sound analytics system (50) learns from the plurality of sound signals by adding an updated model from an external source, where the updated model from the external source are obtained based on a plurality of experiments performed on the machine in a plurality of situations.
  • the one or more predefined sound analytics models are updated by identifying a plurality of classes of the plurality of sounds based on the analysed result.
  • the one or more predefined sound analytics models may be trained to identify and classify the plurality of sound signals in real-time, to infer operational information about the machine, as well as information about the quality of the operation and the health of the machine.
  • the sound analytics engine (50) is further configured to send a real time notification to an external computing device upon detecting the one or more faults.
  • the real time notification may include, a graphic, a vibration, a short message service (SMS) message or an alarm sound.
  • the external computing device includes a mobile phone, a tablet, a laptop or a computer.
  • FIG. 2 is a block diagram of an exemplary sound monitoring device (10) of FIG. 1 in accordance with an embodiment of the present disclosure.
  • the device (10) is configured to detect and analyse the sound from a machine.
  • the machine may include one or more machine of a manufacturing plant, one or more air and gas pipeline or a vehicle.
  • the device (10) includes a sound detection device (40), a sound analytics engine (50), a memory device (30), a processor (20) and a plurality of peripheral devices (60).
  • the sound detection device (40) is located in proximity to the machine.
  • the sound detection device (40) is configured to collect a plurality of sound signals in real-time from the machine.
  • the sound detection device (40) may include a microphone.
  • the sound detection device (40) may be a portable sound detection device and located outside a casing (70). In another embodiment, at least one (35) of one or more sound detection devices (40) may be located inside the casing (70). The sound detection device (40) is further configured to generate digital data files including electrical impulses as sound data.
  • the processor (20) of the device (10) is configured to receive the electrical impulses from the sound detection device (40) and store the electrical impulses in the memory device (30).
  • the processor (20) is also configured to acquire one or more predefined sound analytics models associated with the machine.
  • the one or more predefined sound analytics models are machine learning models trained on a plurality of extensive sound signals data collected previously.
  • the machine learning models are trained on the plurality of sound signals about the one or more faults in the machine, as well as an operating condition of the machine. In other words, a series of numerous experiments or field tests are performed on each device (10) to record the sounds of various fault and predictive fault conditions.
  • the automatic troubleshooting using these one or more predefined sound analytics models may be refined based upon the experience and knowledge of expert technicians.
  • Such one or more predefined sound analytics models may be embedded and associated in the memory device (30).
  • the processor (20) is also configured to analyse the plurality of electrical signals based on the one or more predefined sound analytics models.
  • a plurality of diagnostic algorithms identifies and classify the plurality of sound signals using one or more predefined sound analytics models to draw conclusions regarding the existence of one or more current or future problem condition and also draws statistics about operating condition of the machine.
  • the processor (20) is further configured to identify one or more faults of the machine based on an analysed result and one or more predefined sound analytics models.
  • the processor (20) may also be configured to calculate a plurality of operational patterns of the machine and calculate a plurality of operation statistics such as efficiency and performance of the machine.
  • the processor (20) detects leakage of air or gas from a compressed air or gas pipeline or machinery using the leakage sound as the input.
  • the processor (20) is also configured to identify the plurality of sounds from a moving or stationary vehicle and generate intelligence about the health of the vehicle and the subsystems therein and predictive maintenance of the vehicle.
  • the sound analytics system (50) of the device (10) is further configured to update the one or more learning models based on the plurality of sound signals.
  • the sound analytics system (50) receives the plurality of sound signals from the machine and learn continuously from the plurality of sound signals and identify the one or more faults in the machine when such type of sound signals is received in the future.
  • the sound analytic engine (50) further updates the one or more learning models with one or more parameters such as health of the machine, predictive maintenance of the machine and tracking the operations of the machine.
  • the sound analytics engine (50) is further configured to send a real time notification to an external computing device upon detecting the one or more faults.
  • FIG. 3 illustrates a flow chart representing the steps involved in a method (100) for operating the sound monitoring device of FIG. 1 in accordance with an embodiment of the present disclosure.
  • the method (100) includes collecting, by a sound detection device, a plurality of sound signals in real-time from the machine in step 110. In one embodiment, collecting, by a microphone, a plurality of sound signals in real-time from the machine. In some embodiment, the method (100) may include converting the plurality of sounds in the plurality of electrical signals.
  • the method (100) also includes acquiring, by a processor, one or more predefined sound analytics models associated with the machine in step 120.
  • the method (100) may include receiving the plurality of electrical signals from the sound detection device and store the plurality electrical signals in the memory device.
  • the method (100) further includes analysing the plurality of electrical signals based on the one or more predefined sound analytics models in step 130.
  • the method (100) further includes identifying, by the processor, an operating condition of the machine based on an analysed result and the one or more predefined sound analytics models in step 140.
  • identifying, by the processor, the operating condition of the machine based on the analysed result and the one or more predefined sound analytics models may include identifying one or more faults of the machine.
  • identifying, by the sound analytics engine, the one or more faults in the machine based on the analysed result and the one or more predefined sound analytics models may include identifying a plurality of classes of the plurality of sounds based on the analysed result.
  • the method (100) further includes update the one or more predefined sound analytics models based on the plurality of sound signals in step 150.
  • updating, by the sound analytics engine, the one or more predefined sound analytics models based on the plurality of sound signals may include updating the one or more predefined sound analytics models upon calculating one or more operational patterns and one or more operational statistics of the machine.
  • the method (100) may include sending a real time notification to an external computing device upon detecting the one or more faults.
  • the sound monitoring device described above enable a standalone, independent, and complete product which listens to the plurality of sounds and generates intelligence from the plurality of sounds.
  • the device has the necessary computational resources required to carry out the computation. In carrying out these computations, there is no dependency whatsoever on any external computation resources as compared to conventional devices.
  • the device for sound monitoring uses sound as the primary input which means the device is a non-intrusive. The device is very easy to install and deploy for a variety of applications because of non-touch method.
  • the device has ability to learn the sound signatures over time and the parameters of learning model may be adjusted. This means the device may be used to detect a variety of sound signatures, and the usage of the device may be changed over time. It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the disclosure and are not intended to be restrictive thereof.

Abstract

A device for monitoring an operating condition of a machine is disclosed. The device includes a sound detection device located in proximity to the machine and configured to collect a plurality of sound signals in real-time from the machine. The device also includes a processor electrically coupled to the sound detection device. The processor is configured to acquire one or more predefined sound analytics models associated with the machine. The processor is also configured to analyse the plurality of sound signals based on the one or more predefined sound analytics models. The processor is further configured to identify the operating condition of the machine based on an analysed result and the one or more predefined sound analytics models. The device also includes a sound analytics system which is further configured to update the one or more predefined sound analytics models based on the plurality of sound signals.

Description

A DEVICE FOR SOUND BASED MONITORING OF MACHINE OPERATIONS AND
METHOD FOR OPERATING THE SAME
This International Application claims priority from a provisional patent application filed in India having Patent Application No. 201741024830, filed on July 13, 2017 and titled "A SYSTEM AND METHOD FOR SOUND IDENTIFICATION AND CLASSIFICATION".
BACKGROUND
Embodiments of a present disclosure relate to sound analytics and more particularly to, a device for sound based monitoring of machine operations and method for operating the same.
In many areas of manufacturing or engineering, trouble-free operation of a plant depends on proper functioning of the machines used in the plant. To avoid irregular interruptions or damage of the machine, faults should be detected in the initial stage as possible or before a failure of the machine may cause a shutdown. In instances, the failure or beginning of failure of any machine may be accompanied by characteristic sounds. The cause of the undesirable sound needs to be identified for the machine to continue machine's serviceable life. Various fault detection techniques, more particularly to fault detection techniques with acoustic monitoring are available to detect the fault in the early stage or before failure.
Traditional systems utilize a variety of sensors which measure a plurality of parameters such as current, voltages, temperatures or pressures of the machine. Such sensors are fixed to the machine to receive the plurality of parameters. However, such system leads to extra efforts of installation, they may interfere with the operation of the machine, and are not removable or portable.
Furthermore, some system utilizes acoustic sensor which may use sound inputs. However, such acoustic sensors are incapable of analysing complex sounds. Further, such sensors are designed for identifying very specific sound signature and their functionality is unchangeable over time. Furthermore, the available acoustic sensors only use a threshold checking and give an alarm or indication whenever the threshold is crosses. However, such sensors do not provide the in-depth analysis of sound and sometimes leads to ambiguous results.
Furthermore, the available acoustic sensors can only be used to monitor a specific problem with the machines. Such sensors may not be used to monitor overall operations of the machines, and extract statistics about the machine operations as well as machine performance including quality of the operations.
Hence, there is a need for an improved sound monitoring device for a machine to address the aforementioned issues. BRIEF DESCRIPTION
In accordance with an embodiment of the present disclosure, a device for monitoring sound of a machine is provided. The device includes a sound detection device located in proximity to the machine and configured to collect a plurality of sound signals in real-time from the machine. The device also includes a processor electrically coupled to the sound detection device. The processor is configured to acquire one or more predefined sound analytics models associated with the machine. The processor is also configured to analyse the plurality of sound signals based on the one or more predefined sound analytics models. The processor is further configured to identify an operating condition of the machine based on analysed result and the one or more predefined sound analytics models. The device further includes a sound analytics engine operatively coupled to the processor. The sound analytics system is configured to update the one or more predefined models based on the plurality of sound signals.
In accordance with another embodiment of the present disclosure, a method for operating a sound monitoring device is provided. The method includes collecting, by a sound detection device, a plurality of sound signals in real-time from the machine. The method also includes acquiring, by a processor, one or more predefined sound analytics models associated with the machine. The method further includes analysing, by the processor, the plurality of sound signals based on the one or more predefined sound analytics model. The method further includes identifying, by the processor, an operating condition of the machine based on analysed result and the one or more predefined sound analytics models. The method further includes updating, by a sound analytics system, the one or more sound analytics models based on the plurality of sound signals.
To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures. BRIEF DESCRIPTION OF THE DRAWINGS
The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
FIG. 1 illustrates a block diagram of a device for sound based monitoring machine operations in accordance with an embodiment of the present disclosure;
FIG. 2 illustrates a block diagram of an exemplary sound monitoring device of FIG. 1 in accordance with an embodiment of the present disclosure;
FIG. 3 illustrates a flow chart representing the steps involved in a method for operating the sound monitoring device of FIG. 1 in accordance with an embodiment of the present disclosure. Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
DETAILED DESCRIPTION
For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure. The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.
In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms "a", "an", and "the" include plural references unless the context clearly dictates otherwise.
Embodiments of the present disclosure relate to a device for sound based monitoring of machine operations. The device includes a sound detection device located in proximity to the machine and configured to collect a plurality of sound signals in real-time from the machine. The device also includes a processor electrically coupled to the sound detection device. The processor is configured to acquire one or more predefined sound analytics models associated with the machine. The processor is also configured to analyse the plurality of sound signals based on the one or more predefined sound analytics models. The processor is further configured to identify an operating condition of the machine based on analysed result and the one or more predefined sound analytics models. The device further includes a sound analytics engine operatively coupled to the processor. The sound analytics system is further configured to update the one or more sound analytics models based on the plurality of sound signals.
FIG. 1 is a block diagram of a sound monitoring device (10) in accordance with an embodiment of the present disclosure. The device (10) for monitoring sound of a machine is configured to perform edge computing by receiving a plurality of sound signals from the machine. As user herein, the term 'edge computing' refers to a capability of the device (10) to perform local computing within the device and without requiring a connectivity to the servers. As used herein, the term 'sound' includes both audible and inaudible sounds. In other words, 'sounds' includes sounds that are audible to humans, and sounds that are below the human audible range (subsonic) and sounds that are above the human audible range (ultrasonic). In a specific embodiment, the device (10) include a casing configured to enclose sound detection device (40), a processor (20), a sound analytics system (50), a memory device (30) and a plurality of peripheral devices. In one embodiment, the device (10) may include a processor (20), a memory device (30) and a plurality of peripheral devices.
The device (10) also includes a sound detection device (40) located in proximity to the machine. The sound detection device (40) is configured to collect a plurality of sound signals in real-time from the machine. In some embodiment, the sound detection device (40) may include a microphone. In such embodiment, the sound detection device (40) may be located outside the casing. In another embodiment, at least one of one or more sound detection devices (40) may be located inside the casing. The sound detection device (40) is also configured to convert the plurality of sounds in the plurality of electrical signals. Furthermore, the device (10) also includes the processor (20) electrically coupled to the sound detection device (40). The processor (20) is configured to receive the plurality of electrical signals from the sound detection device (40) and store the plurality electrical signals in the memory device (30). The processor (20) is also configured to acquire one or more predefined sound analytics models associated with the machine. The processor (20) is also configured to analyse the plurality of electrical signals based on the one or more predefined sound analytics models. In one embodiment, the one or more predefined sound analytics models may include a plurality of machine learning models. In some embodiments, the one or more predefined sound analytics models may be stored in the memory device (30). The processor (20) is further configured to identify the operating condition of the machine based on an analysed result and the one or more predefined sound analytics models. In a specific embodiment, the processor (20) is further configured to identify one or more faults of the machine based on an analysed result and the one or more predefined sound analytics models.
The device (10) further includes a sound analytics system (50) operatively coupled to the processor (20). The sound analytics system (50) is configured to update the one or more predefined sound analytics models based on the plurality of sound signals. In one embodiment, the sound analytics system (50) may receive the plurality of sound signals and learns from the plurality of sound signals continuously for detecting one or more faults in the future. In another embodiment, the sound analytics system (50) learns from the plurality of sound signals by adding an updated model from an external source, where the updated model from the external source are obtained based on a plurality of experiments performed on the machine in a plurality of situations. The one or more predefined sound analytics models are updated by identifying a plurality of classes of the plurality of sounds based on the analysed result. In a specific embodiment, the one or more predefined sound analytics models may be trained to identify and classify the plurality of sound signals in real-time, to infer operational information about the machine, as well as information about the quality of the operation and the health of the machine.
In some embodiments, the sound analytics engine (50) is further configured to send a real time notification to an external computing device upon detecting the one or more faults. In such embodiment, the real time notification may include, a graphic, a vibration, a short message service (SMS) message or an alarm sound. In a specific embodiment, the external computing device includes a mobile phone, a tablet, a laptop or a computer.
FIG. 2 is a block diagram of an exemplary sound monitoring device (10) of FIG. 1 in accordance with an embodiment of the present disclosure. The device (10) is configured to detect and analyse the sound from a machine. In one embodiment, the machine may include one or more machine of a manufacturing plant, one or more air and gas pipeline or a vehicle. The device (10) includes a sound detection device (40), a sound analytics engine (50), a memory device (30), a processor (20) and a plurality of peripheral devices (60). The sound detection device (40) is located in proximity to the machine. The sound detection device (40) is configured to collect a plurality of sound signals in real-time from the machine. In some embodiment, the sound detection device (40) may include a microphone. In such embodiment, the sound detection device (40) may be a portable sound detection device and located outside a casing (70). In another embodiment, at least one (35) of one or more sound detection devices (40) may be located inside the casing (70). The sound detection device (40) is further configured to generate digital data files including electrical impulses as sound data.
Furthermore, the processor (20) of the device (10) is configured to receive the electrical impulses from the sound detection device (40) and store the electrical impulses in the memory device (30). The processor (20) is also configured to acquire one or more predefined sound analytics models associated with the machine. The one or more predefined sound analytics models are machine learning models trained on a plurality of extensive sound signals data collected previously. The machine learning models are trained on the plurality of sound signals about the one or more faults in the machine, as well as an operating condition of the machine. In other words, a series of numerous experiments or field tests are performed on each device (10) to record the sounds of various fault and predictive fault conditions. The automatic troubleshooting using these one or more predefined sound analytics models may be refined based upon the experience and knowledge of expert technicians. Such one or more predefined sound analytics models may be embedded and associated in the memory device (30). The processor (20) is also configured to analyse the plurality of electrical signals based on the one or more predefined sound analytics models. A plurality of diagnostic algorithms identifies and classify the plurality of sound signals using one or more predefined sound analytics models to draw conclusions regarding the existence of one or more current or future problem condition and also draws statistics about operating condition of the machine. The processor (20) is further configured to identify one or more faults of the machine based on an analysed result and one or more predefined sound analytics models. In some embodiments, the processor (20) may also be configured to calculate a plurality of operational patterns of the machine and calculate a plurality of operation statistics such as efficiency and performance of the machine. In an exemplary embodiment, the processor (20) detects leakage of air or gas from a compressed air or gas pipeline or machinery using the leakage sound as the input. In another exemplary embodiment, the processor (20) is also configured to identify the plurality of sounds from a moving or stationary vehicle and generate intelligence about the health of the vehicle and the subsystems therein and predictive maintenance of the vehicle. The sound analytics system (50) of the device (10) is further configured to update the one or more learning models based on the plurality of sound signals. In one embodiment, the sound analytics system (50) receives the plurality of sound signals from the machine and learn continuously from the plurality of sound signals and identify the one or more faults in the machine when such type of sound signals is received in the future. The sound analytic engine (50) further updates the one or more learning models with one or more parameters such as health of the machine, predictive maintenance of the machine and tracking the operations of the machine. In some embodiments, the sound analytics engine (50) is further configured to send a real time notification to an external computing device upon detecting the one or more faults.
FIG. 3 illustrates a flow chart representing the steps involved in a method (100) for operating the sound monitoring device of FIG. 1 in accordance with an embodiment of the present disclosure. The method (100) includes collecting, by a sound detection device, a plurality of sound signals in real-time from the machine in step 110. In one embodiment, collecting, by a microphone, a plurality of sound signals in real-time from the machine. In some embodiment, the method (100) may include converting the plurality of sounds in the plurality of electrical signals.
The method (100) also includes acquiring, by a processor, one or more predefined sound analytics models associated with the machine in step 120. In one embodiment, the method (100) may include receiving the plurality of electrical signals from the sound detection device and store the plurality electrical signals in the memory device. The method (100) further includes analysing the plurality of electrical signals based on the one or more predefined sound analytics models in step 130.
The method (100) further includes identifying, by the processor, an operating condition of the machine based on an analysed result and the one or more predefined sound analytics models in step 140. In one embodiment, identifying, by the processor, the operating condition of the machine based on the analysed result and the one or more predefined sound analytics models may include identifying one or more faults of the machine. In such embodiment, identifying, by the sound analytics engine, the one or more faults in the machine based on the analysed result and the one or more predefined sound analytics models may include identifying a plurality of classes of the plurality of sounds based on the analysed result. The method (100) further includes update the one or more predefined sound analytics models based on the plurality of sound signals in step 150. In some embodiments, updating, by the sound analytics engine, the one or more predefined sound analytics models based on the plurality of sound signals may include updating the one or more predefined sound analytics models upon calculating one or more operational patterns and one or more operational statistics of the machine. In a preferred embodiment, the method (100) may include sending a real time notification to an external computing device upon detecting the one or more faults.
Various embodiments of the sound monitoring device described above enable a standalone, independent, and complete product which listens to the plurality of sounds and generates intelligence from the plurality of sounds. The device has the necessary computational resources required to carry out the computation. In carrying out these computations, there is no dependency whatsoever on any external computation resources as compared to conventional devices. Furthermore, the device for sound monitoring uses sound as the primary input which means the device is a non-intrusive. The device is very easy to install and deploy for a variety of applications because of non-touch method.
Moreover, the device has ability to learn the sound signatures over time and the parameters of learning model may be adjusted. This means the device may be used to detect a variety of sound signatures, and the usage of the device may be changed over time. It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the disclosure and are not intended to be restrictive thereof.
While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.
The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.

Claims

WHAT WE CLAIM IS:
1. A device (10) for monitoring an operating condition of a machine comprising: a sound detection device (40) located in proximity to the machine and configured to collect a plurality of sound signals in real-time from the machine; a processor (20) electrically coupled to the sound detection device (40) and configured to: acquire one or more predefined sound analytics models associated with the machine; analyse the plurality of sound signals based on the one or more predefined sound analytics models; identify the operating condition of the machine based on an analysed result and the one or more predefined sound analytics models; a sound analytics system (50) operatively coupled to the processor (20) and configured to update the one or more predefined sound analytics models based on the plurality of sound signals.
2. The device (10) as claimed in claim 1, wherein the sound detection device (40) comprises a microphone.
3. The device (10) as claimed in claim 1, wherein the sound analytics system (50) is further configured to send a real time notification to an external computing device upon detecting the one or more faults.
4. The device is claimed in claim 3, wherein the real time notification comprises, a graphic, a vibration, a short message service (SMS) message or an alarm sound.
5. The device as claimed in claim 3, wherein the external computing device comprises a mobile phone, a tablet, a laptop or a computer.
6. The device (10) as claimed in claim 1, further comprising a memory device (30) and a plurality of peripheral devices (60).
7. The device (10) as claimed in claim 1, further comprising a casing (70) configured to house the sound detection device (40), the processor (20), the sound analytics system (50), the memory (30) and the plurality of peripheral devices (60).
8. The device (10) is claimed in claim 7, wherein the sound detection device (40) is located outside the casing (70).
9. The device (10) is claimed in claim 1, wherein the sound analytics system (50) is further configured to learn from the plurality of sound signals by adding an updated model from an external source.
10. A method (100) comprising: collecting, by a sound detection device, a plurality of sound signals in real-time from a machine; (110) acquiring, by a process, one or more predefined sound analytics models associated with the machine; (120) analysing, by the processor, the plurality of sound signals based on the one or more predefined sound analytics models; (130) identifying, by the processor, an operating condition of the machine based on an analysed result and the one or more predefined sound analytics models; (140) updating, by a sound analytics system, the one or more predefined sound analytics models based on the plurality of sound signals. (150)
11. The method as claimed in claim 10, wherein identifying, by the processor, the operating condition of the machine based on the analysed result and the one or more predefined sound analytics models comprises identifying one or more faults of the machine.
12. The method (100) as claimed in claim 11, wherein identifying, by the processor, the one or more faults in the machine comprises identifying a plurality of classes of the plurality of sounds based on the analysed result.
13. The method (100) as claimed in claim 10, wherein updating, by the sound analytics system, the one or more learning models based on the plurality of sound signals comprises updating the one or more learning models upon calculating one or more operational patterns and one or more operational statistics of the machine.
14. The method (100) as claimed in claim 10, further comprising sending a real time notification to an external computing device upon detecting the one or more faults.
PCT/IB2018/055097 2017-07-13 2018-07-11 A device for sound based monitoring of machine operations and method for operating the same WO2019012437A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2020523832A JP2020527816A (en) 2017-07-13 2018-07-11 Devices for voice-based monitoring of machine operations and how to operate them
US16/627,176 US10976730B2 (en) 2017-07-13 2018-07-11 Device for sound based monitoring of machine operations and method for operating the same

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IN201741024830 2017-07-13
IN201741024830 2017-07-13

Publications (1)

Publication Number Publication Date
WO2019012437A1 true WO2019012437A1 (en) 2019-01-17

Family

ID=65001936

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2018/055097 WO2019012437A1 (en) 2017-07-13 2018-07-11 A device for sound based monitoring of machine operations and method for operating the same

Country Status (3)

Country Link
US (1) US10976730B2 (en)
JP (1) JP2020527816A (en)
WO (1) WO2019012437A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111007817A (en) * 2019-12-11 2020-04-14 三一重工股份有限公司 Equipment processing workpiece quality detection method and device and computer readable storage medium
US11650551B2 (en) 2019-10-04 2023-05-16 Mitsubishi Electric Research Laboratories, Inc. System and method for policy optimization using quasi-Newton trust region method

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11308545B2 (en) * 2018-10-12 2022-04-19 Accenture Global Solutions Limited Automated order troubleshooting
US20210342211A1 (en) * 2019-01-21 2021-11-04 Hewlett-Packard Development Company, L.P. Fault prediction model training with audio data
US11568731B2 (en) * 2019-07-15 2023-01-31 Apple Inc. Systems and methods for identifying an acoustic source based on observed sound
CN111933177B (en) * 2020-07-23 2024-01-09 安徽声讯信息技术有限公司 Intelligent fault analysis method and system based on machine acoustic wave identification
KR102509699B1 (en) * 2021-01-14 2023-03-14 서울대학교 산학협력단 Sound-based Multi-device Operation Monitoring Method and System for the Same

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160163168A1 (en) * 2014-12-05 2016-06-09 Elwha Llc Detection and classification of abnormal sounds
WO2017112591A1 (en) * 2015-12-20 2017-06-29 Prophecy Sensors, Llc Machine fault detection based on a combination of sound capture and on spot feedback

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3124414B2 (en) * 1993-06-17 2001-01-15 株式会社東芝 Monitoring and control equipment
JP2002140090A (en) * 2000-11-02 2002-05-17 Toshiba Corp Abnormality monitor device
KR101472401B1 (en) 2009-07-31 2014-12-12 엘지전자 주식회사 Diagnostic system and method for home appliance
US8964995B2 (en) 2012-09-07 2015-02-24 International Business Machines Corporation Acoustic diagnosis and correction system
US9223299B2 (en) 2012-11-30 2015-12-29 Discovery Sound Technology, Llc Equipment sound monitoring system and method
JP5709327B2 (en) * 2013-05-23 2015-04-30 東芝エレベータ株式会社 Man conveyor abnormality diagnosis system
US20180158288A1 (en) * 2014-04-10 2018-06-07 Twin Harbor Labs Llc Methods and apparatus for notifying a user of the operating condition of a household appliance
JP6377592B2 (en) * 2015-11-09 2018-08-22 日本電信電話株式会社 Abnormal sound detection device, abnormal sound detection learning device, method and program thereof
GB2545257A (en) 2015-12-10 2017-06-14 Gm Global Tech Operations Llc Internal combustion engine comprising a shifting cam system for variable valve actuation

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160163168A1 (en) * 2014-12-05 2016-06-09 Elwha Llc Detection and classification of abnormal sounds
WO2017112591A1 (en) * 2015-12-20 2017-06-29 Prophecy Sensors, Llc Machine fault detection based on a combination of sound capture and on spot feedback

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11650551B2 (en) 2019-10-04 2023-05-16 Mitsubishi Electric Research Laboratories, Inc. System and method for policy optimization using quasi-Newton trust region method
CN111007817A (en) * 2019-12-11 2020-04-14 三一重工股份有限公司 Equipment processing workpiece quality detection method and device and computer readable storage medium

Also Published As

Publication number Publication date
US20200159201A1 (en) 2020-05-21
US10976730B2 (en) 2021-04-13
JP2020527816A (en) 2020-09-10

Similar Documents

Publication Publication Date Title
US10976730B2 (en) Device for sound based monitoring of machine operations and method for operating the same
US20200233397A1 (en) System, method and computer-accessible medium for machine condition monitoring
US8825567B2 (en) Fault prediction of monitored assets
KR20140059697A (en) Service method and server for providing application comprehended user intention
Natesha et al. Fog-based intelligent machine malfunction monitoring system for industry 4.0
KR102270347B1 (en) Apparatus for detecting abnormal situation using deep learning ensemble model and method thereof
JP7068246B2 (en) Abnormality judgment device and abnormality judgment method
WO2018136915A1 (en) System and methods of novelty detection using non-parametric machine learning
US20200409653A1 (en) Intelligent Audio Analytic Apparatus (IAAA) and Method for Space System
EP3759789B1 (en) System and method for audio and vibration based power distribution equipment condition monitoring
CN112131907A (en) Method and device for training classification model
CN113568812A (en) State detection method and device for intelligent robot
JP6729577B2 (en) Signal detecting device, signal detecting method and program
Cai et al. A pipeline leak classification and location estimation system with convolutional neural networks
Verma et al. Android app for intelligent CBM
US11422527B2 (en) Automatic inspection system
KR20220056782A (en) System and method for monitoring a machine
WO2019097412A1 (en) System and method for multimedia-based performance monitoring of an equipment
JP2015064766A (en) Portable terminal and device diagnostic method
Ooi et al. Non-intrusive operation status tracking for legacy machines via sound recognition
RU2793797C2 (en) Intelligent audio-analytical device and method for spacecrafts
JP2016212560A (en) Abnormality symptom detection system and abnormality symptom detection method
JPWO2020183845A1 (en) Sound processing method
US20230058503A1 (en) Notification device, wearable device and notification method
Tossavainen Sound based fault detection system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18831090

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020523832

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18831090

Country of ref document: EP

Kind code of ref document: A1